Q-Learning Networks
NoisyNet-Dueling
Introduced by Fortunato et al. in Noisy Networks for ExplorationNoisyNet-Dueling is a modification of a Dueling Network that utilises noisy linear layers for exploration instead of $\epsilon$-greedy exploration as in the original Dueling formulation.
Source: Noisy Networks for Exploration
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Atari Games | 1 | 33.33% |
| Efficient Exploration | 1 | 33.33% |
| Reinforcement Learning (RL) | 1 | 33.33% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
Dueling Network
|
Q-Learning Networks | |
Noisy Linear Layer
|
Randomized Value Functions |
